Self-Hinting Language Models Enhance Reinforcement Learning
Baohao Liao
baohao
AI & ML interests
NLP
Recent Activity
updated
a model about 6 hours ago
baohao/byt5-base-optim_clean-final_fold5-3_ep20bs1x8lr8e-5_bestavg3 published
a model about 6 hours ago
baohao/byt5-base-optim_clean-final_fold5-3_ep20bs1x8lr8e-5_bestavg3 updated
a model about 6 hours ago
baohao/byt5-base-optim_clean-final_fold5-2_ep20bs2x16lr1e-4_bestavg3 Organizations
models 32
baohao/byt5-base-optim_clean-final_fold5-3_ep20bs1x8lr8e-5_bestavg3
0.6B • Updated
baohao/byt5-base-optim_clean-final_fold5-2_ep20bs2x16lr1e-4_bestavg3
0.6B • Updated
baohao/byt5-base-optim_clean-final_fold5-1_ep10bs2x16lr1e-4_bestavg3
0.6B • Updated
• 15
baohao/byt5-base-optim_clean-final_fold5-0_ep20bs2x16lr1e-4_bestavg3
0.6B • Updated
• 16
baohao/byt5-base-optim_clean-final_fold5-0_ep10bs1x16lr1e-4_bestavg3
0.6B • Updated
• 13
baohao/byt5-base-optim_clean-final_fold5-0_fp32_ep20bs1x16lr2e-4_best
0.6B • Updated
• 11
baohao/byt5-base-optim_clean-final_fold5-0_fp32_ep10bs2x16lr1e-4_bestavg3
0.6B • Updated
• 13
baohao/byt5-base-optim_clean-final_fold5-0_fp32_ep10bs2x16lr1e-4_best
0.6B • Updated
• 12
baohao/byt5-base-optim_clean-final_fold5-0_ep10bs1x8lr1e-4_ep7
0.6B • Updated
• 13
baohao/byt5-xl_clean_fold0_ep10bs4x4lr2e-4_best
4B • Updated
• 15
datasets 26
baohao/hle_rl
Viewer
• Updated
• 30.1k • 5
baohao/hle_sample_trace
Updated
• 9
baohao/sage_validation
Viewer
• Updated
• 1.67k • 16
baohao/luffy_train
Viewer
• Updated
• 15k • 12
baohao/sage_train
Viewer
• Updated
• 15k • 25
baohao/scaf-grpo_train
Viewer
• Updated
• 15k • 10
baohao/olympiadbench
Viewer
• Updated
• 675 • 239
baohao/mmlu_pro
Viewer
• Updated
• 12k • 58
baohao/minerva_math
Viewer
• Updated
• 272 • 188
baohao/math500
Viewer
• Updated
• 500 • 197